Llama-Guard-3-8B · eaddario
Llama-Guard-3-8B Q3_K_L
This file is exactly 3,757,611,392 bytes — 3.50 GiB / 3.76 GB at an effective 3.744 bits per weight. The nominal rate for Q3_K_L is lower; mixed-precision tensors make the real figure higher, always.
From the file· 1 file(s), summed
Get it
3.50 GiB · 1 file
llama.cpp
llama-cli -hf eaddario/Llama-Guard-3-8B-GGUF:Q3_K_L
Downloads and runs in one step, resolving the quantization by name.
Hugging Face CLI
hf download eaddario/Llama-Guard-3-8B-GGUF Llama-Guard-3-8B-Q3_K_L.gguf
Direct download
Straight from the Hugging Face CDN — we host nothing and earn nothing from this. Verify what you received against the exact byte count above; a size mismatch is the usual cause of a file that will not load.
Size
3.50 GiB
3.76 GB
Effective bpw
3.744
from real bytes ÷ params
Tensors
—
Header
—
GGUF metadata